CN109830101A - A kind of congestion regions recognition methods based on abnormal microwave traffic data reparation - Google Patents
A kind of congestion regions recognition methods based on abnormal microwave traffic data reparation Download PDFInfo
- Publication number
- CN109830101A CN109830101A CN201910109047.4A CN201910109047A CN109830101A CN 109830101 A CN109830101 A CN 109830101A CN 201910109047 A CN201910109047 A CN 201910109047A CN 109830101 A CN109830101 A CN 109830101A
- Authority
- CN
- China
- Prior art keywords
- data
- time point
- attribute
- abnormal
- standard time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation, including by when window based on irregular time point data reparation, on the basis of standard time point data collection attribute abnormal data identification and repair, to scheme base exponential smoothing to flow disorder data recognition, and it is repaired by multiple linear regression, obtain the valid data collection after abnormal microwave traffic data is repaired, then speed, flow and time occupancy are concentrated by valid data, carries out the identification in traffic congestion region.The present invention simply and efficiently can carry out data reparation to abnormal microwave traffic data, avoid the interference of noise data, can ensure the accuracy of traffic congestion region recognition.
Description
Technical field
The invention belongs to intelligent transportation fields, are related to a kind of congestion regions identification based on abnormal microwave traffic data reparation
Method.
Background technique
Microwave Vehicle Detection technology is obtaining traffic data as the current important channel for carrying out dynamic transport data gathering and processing
Aspect with its high efficiency, occupy that storage space is small, the simple feature of installation maintenance has obtained extremely wide application.Microwave traffic
Detection is changed through A/D conversion, fast Fourier transform algorithm by motor vehicle based on the different received wave of frequency and back wave
The time-domain analog signal generated when passing through detector is converted into frequency domain digital signal, and friendship is obtained finally by microwave difference frequency signal
Logical data.
However in the road traffic detection system of actual cities, the data for the real-time detection that microwave acquisition technique obtains are not
Entirely accurate, these data often because by traffic detector hardware fault, external electromagnetic wave interference, communication failure, it is non-just
, there is the problems such as shortage of data, error in data, data redundancy and data exception, significantly in the influence of the factors such as normal traffic behavior
Weaken the effect of the traffic administration and control measure formulated based on data.
Currently, the restorative procedure of abnormal data lays particular emphasis on the height to metadata from general applicability angle mostly
Efficiency is scanned with the accurate location for the data that note abnormalities in time, since it has general applicability, causes how to repair
It is difficult to provide feasible method in the method for multiple exception number, the reparation of abnormal microwave traffic data can be used for directly not yet
The data of guide data user's real work repair system.
Summary of the invention
Technical problem: the present invention provides a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation,
The method achieve the rejecting of reparation, wrong data to microwave missing data and the reparations of abnormal data, it is ensured that microwave is handed over
The quality of logical data, enables data to correctly react true traffic noise prediction, is traffic administration, planning, design portion
Door formulates effective control policy, traffic programme, design scheme and provides reasonable data supporting.
Technical solution: the congestion regions recognition methods of the invention based on abnormal microwave traffic data reparation, including it is following
Step:
1) in raw microwave traffic data, based on when window [t+ (n-1) T, t+nT) to irregular time point data
It is repaired, obtains standard time point data collection, T is the collection period of microwave detector；T is some standard time point, takes T whole
At the time of any time of several times namely microwave detector carry out certain vehicle data typing；N is positive integer；
2) on the basis of standard time point data collection, according to the flow of every vehicle data, speed and time occupancy three
Item attribute value condition is identified and is repaired to attribute abnormal data, and attribute abnormal repair data collection is obtained；
3) on the basis of attribute abnormal repair data collection, flow abnormal data is identified and is repaired, obtained abnormal micro-
Valid data collection after the reparation of wave traffic data；
4) speed, flow and the time occupancy concentrated according to valid data, identifies traffic congestion region.
Further, in the method for the present invention, when the raw microwave traffic data refers to that motor vehicle crosses microwave detector,
Detector just carries out a vehicle data typing every a collection period, and every data included vehicle time, lane number, stream
Amount, speed and time occupancy.
Further, in the method for the present invention, irregular time point data is carried out as follows in the step 1)
It repairs:
1.1) it initializes, enables n=1；
If window when 1.2) [t+ (n-1) T, t+nT) in without vehicle data, then the period is denoted as the shortage of data period
And rejected, it enters step 1.5), otherwise enters step 1.3)；
If window when 1.3) [t+ (n-1) T, t+nT) in an only vehicle data, then by the speed of the vehicle data,
When flow, time occupancy vehicle attribute value are as standard time point t+ (n-1) T, the speed of vehicle data, flow, time
1.5) occupancy attribute value, enters step, otherwise enter step 1.4)；
1.4) this constantly window [t+ (n-1) T, t+nT) in have a plurality of vehicle data, then by all vehicles in window when this
The vehicle when speeds of data, flow, time occupancy attribute mean value are as standard time point t+ (n-1) T, in vehicle data
Speed, flow, time occupancy attribute value；
1.5) n=n+1 is enabled, if n≤N, return step 1.1) vehicle data in window of lower a period of time is judged, otherwise
Export the revised data set of vehicle data namely standard time point data collection, whereinToIndicate microwave detector
Detection total duration.
Further, in the method for the present invention, attribute abnormal data are identified as follows in the step 2):
2.1) it initializes, enables m=1；
2.2) it is concentrated in standard time point data, if when standard time point t+mT, the speed attribute value of vehicle data
Vt+m·T, flow attribution value Qt+m·T, time occupancy attribute value Dt+m·TIt " does not lack ", then enters step 2.3), otherwise should
The vehicle data of standard time point is denoted as attribute missing data, enters step 2.5)；
2.3) when according to following below scheme to standard time point t+mT, speed, the flow attribution value of vehicle data are sentenced
Other:
If Step a Vt+m·T<1.25·VDAnd Qt+m·T2.4) < C then enters step, otherwise enters step b；
If Step b Vt+m·T>1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as speed attribute by < C
Beyond data, enters step 2.4), otherwise enter step c；
If Step c Vt+m·T<1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as flow attribution by > C
It beyond data, enters step 2.4), is otherwise denoted as speed and flow attribution beyond data, enters step 2.4)；
If 2.4) in the vehicle data of standard time point t+mT, Vt+m·T、Qt+m·T、Dt+m·TIn exist simultaneously numerical value and be equal to
0 and the attribute not equal to 0, then the vehicle data of the standard time point is denoted as attribute error data, entered step 2.5), otherwise
Speed, flow attribution value when showing standard time point t+mT is normal, is directly entered step 2.5)；
2.5) m=m+1 is enabled, if m≤M, M are the data volume of standard data set, then return step 2.2) to next standard when
Between the vehicle data put judged that otherwise output attribute missing data, attribute exceed data, attribute error data, and be referred to as
For attribute abnormal data.
Further, in the method for the present invention, attribute abnormal data are repaired in the step 2), are according to same micro-
The historical data of wave detector carries out according to the following formula:
Wherein,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Value after flow, the reparation of time occupancy attribute, i is positive integer, Vt+(i-2)·T、Vt+(i-1)·T、Vt+(i+1)·T、Vt+(i+2)·TRespectively
Indicate microwave detector typing when standard time point is t+ (i-2) T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T
Vehicle data speed attribute value, Qt+(i-2)·T、Qt+(i-1)·T、Qt+(i+1)·T、Qt+(i+2)·TRespectively indicating standard time point is t+
(i-2) when T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T the vehicle data of the microwave detector typing flow category
Property value, Dt+(i-2)·T、Dt+(i-1)·T、Dt+(i+1)·T、Dt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t+ (i-1)
T, when t+ (i+1) T, t+ (i+2) T the vehicle data of the microwave detector typing time occupancy attribute value.
Further, in the method for the present invention, attribute abnormal data are repaired in the step 2), are according to adjacent inspection
The data of device same period are surveyed, are carried out according to the following formula:
Wherein,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Flow, time occupancy attribute reparation value,Respectively indicating should when standard time point is t+iT
The speed attribute value of the vehicle data of four adjacent microwave detector typings before and after microwave detector,It is micro- to respectively indicate adjacent before and after the microwave detector when standard time point is t+nT four
The flow attribution value of the vehicle data of wave detector typing,Respectively indicating standard time point is t+
The time occupancy attribute value of the vehicle data of four microwave detector typings adjacent before and after microwave detector when iT.
Further, in the method for the present invention, flow abnormal data is identified as follows in the step 3):
3.1) it is concentrated in attribute abnormal repair data, takes the flow attribution value of four groups of vehicle datas at adjacent modular time point
Qt+(j-2)·T、Qt+(j-1)·T、Qt+j·T、Qt+(j+1)·TMedian construct primary smooth sequence
3.2) it takesMedian construct secondary smooth sequence
3.3) it enablesConstruct smooth sequence three times
3.4) it calculatesWith Qt+j·TRoot-mean-square errorM is standard data set
Data volume and attribute abnormal repair data collection data volume；
3.5) when taking standard time point t+jT, the flow attribution value of vehicle data is maximum, minimum value is respectively as follows:
If 3.6)Then think flow number when standard time point t+jT
Flow attribution value according to vehicle data when exception namely standard time point t+jT is abnormal, needs to be modified, otherwise it is assumed that should
Flow is normal, without being modified.
Further, different to flow according to the following formula according to multiple linear regression in the step 3) in the method for the present invention
Regular data is repaired:
Ct+u·T=a0+a1·1Qt+u·T+a2·2Qt+u·T+…ar·rQt+u·T+e
Wherein, Ct+n·TFor the value after the abnormal flow data correction of standard time point t+nT,1Qt+u·T、2Qt+u·T、…、rQt+u·TDevice r normal discharge data, a in the collected history of same standard time point t+uT are surveyed for the microwave0For constant
, a1、a2…arFor regression coefficient, e is random error.
Microwave Vehicle Detection technology is based on receiving the back wave different from tranmitting frequency, through A/D conversion, quick Fourier
The time-domain analog signal that the technologies such as leaf transfer algorithm (FFT) variation generate when motor vehicle is passed through detector is converted into frequency domain digital
Signal, and by microwave difference frequency signal obtain relevant traffic flow data, every data included the vehicle time, flow, spot spe J,
Many attribute informations such as time occupancy, lane number, driving direction.
The present invention is based on vehicle time, flow, 4 speed, time occupancy attributes is spent in microwave data, from following three
Aspect ensures the integrality of microwave traffic data, validity: 1) reparation of irregular time point data；2) attribute abnormal data
Identification and reparation；3) identification and reparation of Traffic Anomaly data.
In a first aspect, the reparation of the irregular time point data be based on when window realize.Microwave detector can be each
Standard time clicks through the acquisition of row data, but is influenced by extraneous or apparatus factor, the time point of microwave detector actual acquired data
There can be error with standard time point, this kind of irregular time point data need to be repaired.With microwave data collection period T and mark
Window (t+ (n-1) T, t+nT) when quasi- time point t is constructed.Wherein, t takes any time of T integral multiple, the inspection of microwave detector
Survey total duration is T0, then data includeWindow when a, n=1,2 ..., N.Several microwave numbers can be contained when each in window
According to, and every data included vehicle time, the volume of traffic, speed, time occupancy attribute information.When window building is irregular when foundation
Between point data restorative procedure it is as follows:
Step1 initialization, enables n=1；
If window when Step2 [t+ (n-1) T, t+nT) in without vehicle data, then the period is denoted as the shortage of data period
And rejected, into Step5, otherwise enter Step3；；
If window when Step3 [t+ (n-1) T, t+nT) in an only vehicle data, then by the vehicle of the vehicle data
When speed, flow, time occupancy vehicle attribute value are as standard time point t+ (n-1) T, the speed of vehicle data, flow, when
Between occupancy attribute value, into Step5, otherwise enter Step4；
Step4 this constantly window [t+ (n-1) T, t+nT) in have a plurality of vehicle data, then by all vehicles in window when this
The vehicle when speeds of data, flow, time occupancy attribute mean value are as standard time point t+ (n-1) T, in vehicle data
Speed, flow, time occupancy attribute value；
Step 5 enables n=n+1, if n≤N, returns to Step 1 and judges the vehicle data in window of lower a period of time, otherwise
Export the revised data set of vehicle data namely standard time point data collection.
Second aspect, the identification and reparation of the attribute abnormal data are based on standard time point data collection, including belong to
The identification of sexual abnormality data and attribute abnormal data repair two steps.
Further, whether attribute abnormal data identification is lacked with three flow, speed and time occupancy attribute values
Or rationally based on, the recognition methods of attribute abnormal data is as follows:
Step 1 is initialized, and enables m=1；
Step 2 is concentrated in standard time point data, if when standard time point t+mT, the speed attribute value of vehicle data
Vt+m·T, flow attribution value Qt+m·T, time occupancy attribute value Dt+m·TIt " does not lack ", then enters Step3, otherwise by the standard
The vehicle data at time point is denoted as attribute missing data, into Step5；
Step 3 according to following below scheme to standard time point t+mT when, the speed of vehicle data, flow attribution value carry out
Differentiate:
If Step a Vt+m·T<1.25·VDAnd Qt+m·T< C then enters Step4, otherwise enters Stepb；
If Step b Vt+m·T>1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as speed attribute by < C
Beyond data, into Step4, otherwise enter Stepc；
If Step c Vt+m·T<1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as flow attribution by > C
Beyond data, into Step4, speed and flow attribution are otherwise denoted as beyond data, into Step5；
If in the vehicle data of Step 4 standard time point t+mT, Vt+m·T、Qt+m·T、Dt+m·TIn exist simultaneously numerical value etc.
In 0 and the attribute not equal to 0, then the vehicle data of the standard time point is denoted as attribute error data, into Step5, otherwise
Speed, flow attribution value when showing standard time point t+mT is normal, is directly entered Step5；
Step 5 enables m=m+1, if m≤M, M are the data volume of standard data set, then returns to Step2 to next standard time
The vehicle data of point is judged that otherwise output attribute missing data, attribute exceed data, attribute error data, and be referred to as
Attribute abnormal data.
Further, the attribute abnormal data for being t+mT to standard time point, have based on same microwave detector history
The modification method of data and two kinds of modification method based on the same period data of adjacent microwave detector.
Wherein, the modification method based on same microwave detector historical data is according to same detector in the abnormal time
The data of the 4 standard time points in point front and back are repaired to obtain attribute abnormal repair data collection, and speed, flow and time occupy
The revised value of rate abnormal attribute is as follows:
In formula,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Value after flow, the reparation of time occupancy attribute, Vt+(i-2)·T、Vt+(i-1)·T、Vt+(i+1)·T、Vt+(i+2)·TWhen respectively indicating standard
Between point be t+ (i-2) T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T when the microwave detector typing vehicle data
Speed attribute value, Qt+(i-2)·T、Qt+(i-1)·T、Qt+(i+1)·T、Qt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t
The flow attribution value of the vehicle data of microwave detector typing when+(i-1) T, t+ (i+1) T, t+ (i+2) T,
Dt+(i-2)·T、Dt+(i-1)·T、Dt+(i+1)·T、Dt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t+ (i-1) T, t+
(i+1) when T, t+ (i+2) T the vehicle data of the microwave detector typing time occupancy attribute value.
Wherein, the modification method based on the same period data of adjacent microwave detector is different at this according to adjacent 4 detectors
The data at normal time point are repaired to obtain attribute abnormal repair data collection, speed, flow and time occupancy abnormal attribute
Reparation value it is as follows:
In formula,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Flow, time occupancy attribute reparation value,Indicate microwave when standard time point is t+iT
The speed attribute value of the vehicle data of four adjacent microwave detector typings before and after detector,
Indicate the vehicle data of four microwave detector typings adjacent before and after the microwave detector when standard time point is t+nT
Flow attribution value,Indicate adjacent before and after the microwave detector when standard time point is t+iT
The time occupancy attribute value of the vehicle data of four microwave detector typings.
The third aspect, the Traffic Anomaly data identification and reparation are based on attribute abnormal repair data collection, including stream
Measure the identification of abnormal data and two steps of reparation of Traffic Anomaly data.
Further, the identification of Traffic Anomaly data is based on attribute abnormal repair data collection, by figure base exponential smoothing
For reasonable dynamic flow threshold value come what is realized, Traffic Anomaly data identification method is as follows:
Step 1 is concentrated in attribute abnormal repair data, takes the flow attribution of four groups of vehicle datas at adjacent modular time point
Value Qt+(j-2)·T、Qt+(j-1)·T、Qt+j·T、Qt+(j+1)·TMedian construct primary smooth sequence
Step 2 takesMedian construct secondary smooth sequence
Step 3 is enabledConstruct smooth sequence three times
Step 4 is calculatedWith Qt+j·TRoot-mean-square errorM is normal data
The data volume of collection does not carry out data rejecting to standard data set when repairing because of attribute abnormal data, therefore M also repairs for attribute abnormal
The data volume of complex data collection；
Step 5 is to smooth sequenceIt is modified by RMSE value with the reasonable dynamic threshold of determination:
In formula, Qmax(t+j·T)、Qmin(t+jT) when respectively indicating standard time point t+jT, the flow of vehicle data
Attribute value maximum, minimum value；
If Step 6Then think flow when standard time point t+jT
Data exception namely when standard time point t+jT vehicle data flow attribution value it is abnormal, need to be modified, otherwise it is assumed that
The flow is normal, without being modified.
Further, the standard time point t+uT occurred to Mr. Yu's Traffic Anomaly data can survey device according to the microwave and exist
The same collected r normal discharge data in history of standard time point1Qt+u·T、2Qt+u·T、…、rQt+u·T, construct multiple linear
Regression model is repaired to obtain valid data:
Ct+u·T=a0+a1·1Qt+u·T+a2·2Qt+u·T+…ar·rQt+u·T+e
Wherein, Ct+n·TFor the value after the abnormal flow data correction of standard time point t+nT, a0For constant term, a1、
a2…arFor regression coefficient, e is random error.
The utility model has the advantages that compared with prior art, the present invention having the advantage that
Traffic data be formulate traffic control measure basic basis, and at present mostly abnormal data restorative procedure from
General applicability angle is set out, it is difficult to directly bring the real work for instructing microwave traffic data user.Unreasonable microwave
Traffic data is difficult to reflect true traffic condition, will cause the mismatch of management and control measures Yu actual traffic problem.Side of the present invention
Method realizes the reparation to time point data irregular in initial data, lacks, exceeds and wrong three classes attribute abnormal data
Identification and reparation, and according to the flow connection between the changes in flow rate rule of single microwave detector acquisition and adjacent microwave detector
System, using figure base exponential smoothing and multiple regression analysis, realizes the identification and reparation of Traffic Anomaly data, it is ensured that data acquired
Meet actual traffic rheology law.The present invention realizes the reparation of abnormal microwave traffic data, it is ensured that data can be correct
The anyway actual traffic condition in ground can formulate effective control policy for traffic administration, planning, design department, traffic programme, set
Meter scheme provides reasonable data supporting.
Detailed description of the invention
Fig. 1 is microwave signal pretreatment process figure；
Fig. 2 is that abnormal microwave data repairs overall flow figure
Fig. 3 is that irregular time point data repairs flow chart
Fig. 4 is attribute abnormal data identification process figure
Fig. 5 is that attribute abnormal data repair flow chart
Fig. 6 is that Traffic Anomaly data repair overall flow figure
Fig. 7 is Traffic Anomaly data identification process figure
Fig. 8 is that Traffic Anomaly data repair flow chart
Specific embodiment
Below in conjunction with attached drawing, the invention will be further described.
As shown in Figure 1, the acquisition of microwave traffic data is to pre-process to realize by wave frequency, with the different received wave of frequency
Based on back wave, and through A/D conversion, fast Fourier transform algorithm (FFT) change technique by motor vehicle device after testing
When the time-domain analog signal that generates be converted into frequency domain digital signal, and relevant traffic flow data is obtained by microwave difference frequency signal,
Every data included many attributes such as vehicle time, speed, time occupancy, lane number, driving direction, the present invention mainly according to
According to the quality control for crossing vehicle time, the volume of traffic, speed and time occupancy attribute progress microwave data.
As shown in Fig. 2, a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation, including following three
Aspect: firstly, based on when window construct the restorative procedure of irregular time point data, raw microwave data are handled to obtain
Standard time point data collection.Secondly, on the basis of standard time point data collection, in conjunction with the volume of traffic, speed and time occupancy, vehicle
Road number building attribute abnormal restorative procedure is to lacking, exceed and wrong three classes attribute abnormal data identify, and by phase
Adjacent period data or adjacent microwave detector data repair attribute abnormal data, obtain attribute abnormal repair data collection.
Then, on the basis of attribute abnormal repair data collection, in conjunction with whole day changes in flow rate rule, reasonable flow is determined to scheme base exponential smoothing
Dynamic threshold, identify Traffic Anomaly data, and repaired to flow abnormal data using multiple linear regression model, finally
Obtain effective microwave data collection.
In general, microwave detector is to click through row data in the standard time to acquire, but because of equipment fault, other signals
Interference and Assessment on Environmental Impact Affected, the microwave detector practical time point for carrying out data acquisition can have error with standard time point, make
The phenomenon that being lost at standard time data.As shown in figure 3, irregular time point data be based on when window repaired, it is micro-
Wave data collection cycle T takes the detection cycle of microwave detector, and the standard time, point t took any time of T integral multiple, as the period is
5 minutes, then the standard time can use any time in 00:00:00,00:05:00,00:10:00 ... 24:00:00.According to when
Data in window (t+ (n-1) T, t+nT) repair the data of standard time point t, when the detection of microwave detector is total
A length of T0, then data includeWindow when a, n=1,2 ..., N.Window includes several microwave datas when each, and every number
According to including vehicle time, the volume of traffic, speed, time occupancy attribute information, window and when irregular data attribute building when foundation
Between point data restorative procedure it is as follows:
Step1 initialization, enables n=1；
If window when Step2 [t+ (n-1) T, t+nT) in without vehicle data, then the period is denoted as the shortage of data period
And rejected, into Step5, otherwise enter Step3；
If window when Step3 [t+ (n-1) T, t+nT) in an only vehicle data, then by the vehicle of the vehicle data
When speed, flow, time occupancy vehicle attribute value are as standard time point t+ (n-1) T, the speed of vehicle data, flow, when
Between occupancy attribute value, into Step5, otherwise enter Step4；
Step4 this constantly window [t+ (n-1) T, t+nT) in have a plurality of vehicle data, then by all vehicles in window when this
The vehicle when speeds of data, flow, time occupancy attribute mean value are as standard time point t+ (n-1) T, in vehicle data
Speed, flow, time occupancy attribute value；
Step 5 enables n=n+1, if n≤N, returns to Step 1 and judges the vehicle data in window of lower a period of time, otherwise
Export the revised data set of vehicle data namely standard time point data collection.
Correspondence between realizing microwave data when detecting by the reparation of aforementioned irregular time point data on point, at this time
Three flow included by every data, speed and time occupancy attribute values have " 0 ", " be greater than 0 ", three kinds of " missing (/) "
Situation is needed at this time to attribute that value is "/", value is " 0 " but does not meet the attribute of convention and value is " being greater than 0 " but beyond threshold value
Attribute is analyzed with recognition property abnormal data.As shown in figure 4, the identification of attribute abnormal data is in standard time point data
Differentiate on the basis of collection by missing, threshold value differentiates and mistake is sentenced and judged three attribute values, definition missing exceeds and mistake
Three attribute abnormal datas.It is missing data if taking "/" based on whether the identification of missing data takes "/" by attribute value.It is super
The identification of data is realized according to threshold value diagnostic method out, and the investigation discovery road actual vehicle speed value upper limit is generally design speed
125%, speed is defined using the 125% of design speed as speed threshold value beyond data；Road traffic flow is not to be exceeded
The road maximum traffic capacity defines flow using the road maximum traffic capacity as flow threshold beyond data.The knowledge of wrong data
Do not differentiated according to the value relationship of each attribute, for include in microwave data speed, flow and time occupancy three
Attribute is denoted as wrong data if existing simultaneously the attribute equal to 0 and not equal to 0 in three attributes.Further, by speed
It is zero and data definition that flow or time occupancy are not zero is speed wrong data, is zero by flow and speed or time account for
It is flow wrong data with the definition that rate is not zero, is zero by time occupancy and definition that flow or speed are not zero is the time
Occupancy wrong data.The specific identification step of attribute abnormal data is as follows:
Step 1 is initialized, and enables m=1；
Step 2 is concentrated in standard time point data, if when standard time point t+mT, the speed attribute value of vehicle data
Vt+m·T, flow attribution value Qt+m·T, time occupancy attribute value Dt+m·TIt " does not lack ", then enters Step3, otherwise by the standard
The vehicle data at time point is denoted as attribute missing data, into Step5；
Step 3 according to following below scheme to standard time point t+mT when, the speed of vehicle data, flow attribution value carry out
Differentiate:
If Step a Vt+m·T<1.25·VDAnd Qt+m·T< C then enters Step4, otherwise enters Stepb；
If Step b Vt+m·T>1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as speed attribute by < C
Beyond data, into Step4, otherwise enter Stepc；
If Step c Vt+m·T<1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as flow attribution by > C
Beyond data, into Step4, speed and flow attribution are otherwise denoted as beyond data, into Step5；
If in the vehicle data of Step 4 standard time point t+mT, Vt+m·T、Qt+m·T、Dt+m·TIn exist simultaneously numerical value etc.
In 0 and the attribute not equal to 0, then the vehicle data of the standard time point is denoted as attribute error data, into Step5, otherwise
Speed, flow attribution value when showing standard time point t+mT is normal, is directly entered Step5；
Step 5 enables m=m+1, if m≤M, M are the data volume of standard data set, then returns to Step2 to next standard time
The vehicle data of point is judged that otherwise output attribute missing data, attribute exceed data, attribute error data, and be referred to as
Attribute abnormal data.As shown in figure 5, missing, exceeding and wrong three classes attribute abnormal data can be by same detector same
The data mean value of the historical data of period or adjacent microwave detector in the same period is repaired, and is t+ to standard time point
The abnormal attribute data of mT, according to same detector 4 standard time points before and after the data exception time point data into
Row is repaired to obtain attribute abnormal repair data, and the restorative procedure of speed, flow and time occupancy abnormal attribute is as follows:
In formula,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Value after flow, the reparation of time occupancy attribute, Vt+(i-2)·T、Vt+(i-1)·T、Vt+(i+1)·T、Vt+(i+2)·TWhen respectively indicating standard
Between point be t+ (i-2) T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T when the microwave detector typing vehicle data
Speed attribute value, Qt+(i-2)·T、Qt+(i-1)·T、Qt+(i+1)·T、Qt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t
The flow attribution value of the vehicle data of microwave detector typing when+(i-1) T, t+ (i+1) T, t+ (i+2) T,
Dt+(i-2)·T、Dt+(i-1)·T、Dt+(i+1)·T、Dt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t+ (i-1) T, t+
(i+1) when T, t+ (i+2) T the vehicle data of the microwave detector typing time occupancy attribute value.
Can also the data according to adjacent 4 detectors at the data exception time point repaired to obtain attribute abnormal and repair
The reparation value of complex data collection, speed, flow and time occupancy abnormal attribute is as follows:
In formula,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed,
Value after flow, the reparation of time occupancy attribute, Vt+(i-2)·T、Vt+(i-1)·T、Vt+(i+1)·T、Vt+(i+2)·TWhen respectively indicating standard
Between point be t+ (i-2) T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T when the microwave detector typing vehicle data
Speed attribute value, Qt+(i-2)·T、Qt+(i-1)·T、Qt+(i+1)·T、Qt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t
The flow attribution value of the vehicle data of microwave detector typing when+(i-1) T, t+ (i+1) T, t+ (i+2) T,
Dt+(i-2)·T、Dt+(i-1)·T、Dt+(i+1)·T、Dt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t+ (i-1) T, t+
(i+1) when T, t+ (i+2) T the vehicle data of the microwave detector typing time occupancy attribute value.
As shown in fig. 6, the identification of Traffic Anomaly data and reparation of microwave data include day part flow control, Traffic Anomaly
The identification of data, Traffic Anomaly data three steps of reparation.Wherein, day part flow control is real according to road passage capability
It is existing；What the reasonable dynamic flow threshold value for being identified by structure figures base exponential smoothing of Traffic Anomaly data was realized, according to dynamic threshold
The identification to flow abnormal data can be realized in the reasonable flow window that value obtains；The reparation of abnormal flow be according to historical data or
The data on flows of adjacent video detector carries out abnormal data realization by multiple linear regression.As shown in fig. 7, flow is different
The identification of regular data is realized by the reasonable dynamic flow threshold value of figure base exponential smoothing, determines day part according to dynamic threshold
Reasonable flow window, in the data of the flow window, Traffic Anomaly data, Traffic Anomaly data identification side can not regarded as
Method construction step is as follows:
Step 1 is concentrated in attribute abnormal repair data, takes the flow attribution of four groups of vehicle datas at adjacent modular time point
Value Qt+(j-2)·T、Qt+(j-1)·T、Qt+j·T、Qt+(j+1)·TMedian construct primary smooth sequence
Step 2 takesMedian construct secondary smooth sequence
Step 3 is enabledConstruct smooth sequence three times
Step 4 is calculatedWith Qt+j·TRoot-mean-square errorM is normal data
The data volume of collection does not carry out data rejecting to standard data set when repairing because of attribute abnormal data, therefore M also repairs for attribute abnormal
The data volume of complex data collection；
Step 5 is to smooth sequenceIt is modified by RMSE value with the reasonable dynamic threshold of determination:
In formula, Qmax(t+j·T)、Qmin(t+jT) when respectively indicating standard time point t+jT, the flow of vehicle data
Attribute value maximum, minimum value；
If Step 6Then think flow when standard time point t+jT
Data exception namely when standard time point t+jT vehicle data flow attribution value it is abnormal, need to be modified, otherwise it is assumed that
The flow is normal, without being modified.
As shown in figure 8, the standard time point t+uT that Mr. Yu's Traffic Anomaly data occur can be surveyed device according to the microwave and be existed
The same collected r normal discharge data in history of standard time point1Qt+u·T、2Qt+u·T、…、rQt+u·T, construct multiple linear
Regression model is repaired to obtain valid data:
Ct+u·T=a0+a1·1Qt+u·T+a2·2Qt+u·T+…ar·rQt+u·T+e
Wherein, Ct+n·TFor the value after the abnormal flow data correction of standard time point t+nT, a0For constant term, a1、
a2…arFor regression coefficient, e is random error.
Identification and amendment by the Traffic Anomaly data concentrated to attribute abnormal repair data, can be obtained abnormal microwave
Valid data collection after traffic data reparation.The data set ensures the integrality of microwave traffic data, correctness and meets friendship
Logical development law, avoids misleading of the abnormal data to traffic control decision, the formulation for traffic administration and control measure provides
The data supporting of science.
Acquisition of the microwave traffic detector realization to original traffic data is laid in city road, is controlled by aforementioned quality
The valid data collection that method obtains, can carry out congestion regions identification, traffic guidance, road optimization design and speed limit management, avoid
Noise data bring interference, it is ensured that the correctness of scheme, reasonability simultaneously meet actual traffic situation.
Further, speed, the time occupancy, flow progress congestion regions identification concentrated according to valid data, this hair
It is bright to be identified using method comprising the following steps:
The given period for needing to carry out congestion regions identification of Step 1, calculate each detector valid data collection within the period
Average speed, average time occupancy, average flow rate, the traffic capacity and mean flow meter in conjunction with section locating for detector
Calculate traffic loading.Wherein, road section capacity is obtained according to its grade, number of track-lines in conjunction with specification；
Average speed is less than congestion speed to Step 2 or time occupancy is greater than congestion occupancy or traffic loading is greater than
The detector location of congestion load is known as congestion points.Wherein, congestion load takes in related specifications corresponding to level Four service level
Traffic loading, congestion speed take speed corresponding to level Four service level in related specifications, and congestion occupancy takes 0.4~0.6；
All congestion points in survey region, are mainly gathered around by the acquisition of DBSCAN Spatial Clustering in the acquisition of Step 3 city
Stifled region.
Primary object and innovation of the invention is to obtain the valid data collection after abnormal microwave traffic data is repaired.This
The step of above-mentioned Step 1 to Step 3 of invention identifies congestion regions is existing conventional techniques means, the method for the present invention
It, can also be using other existing known methods, as long as being able to achieve to congestion other than carrying out identification process using this mode
The identification in region.
In the method for the present invention, can also it is above-mentioned identify congestion regions on the basis of, for congestion regions, traffic administration institute
Door can formulate traffic guidance scheme by peripheral path, and inform driver by broadcast.
In the present invention, the flow that can also be concentrated according to reasonable data carries out road optimization design, including following three steps
It is rapid:
Step 1 is for the road in congestion regions, and according to category of roads, number of track-lines, it is logical to obtain highway layout in conjunction with specification
Row ability value；
The flow that Step 2 concentrates the valid data after the highway layout traffic capacity and abnormal microwave traffic data reparation
It compares, if design capacity is greater than flow, without carrying out road optimization；If the traffic capacity is less than flow, existing
Road is not able to satisfy current demand, needs to optimize；
Step 3 takes setting for the difference of flow and design capacity and single lane for the road that optimizes of needs
The meter traffic capacity, which is done, to be compared, and the reasonable lane quantity widened when needing to optimize is obtained.
Further, the valid data after repairing according to abnormal microwave traffic data concentrate speed, license plate number to carry out speed limit
Management.For having been carried out the urban road or highway of road speed limit, the speed that speed limit value is concentrated with valid data is compared.
If speed is less than speed limit value, then it is assumed that vehicle safe driving；Otherwise it is assumed that overspeed of vehicle travels, while recording license plate number and uploading
Punishment of putting on record is carried out to administrative department.
Finally, it should be noted that those skilled in the art answers although being illustrated with regard to the method for the present invention and having been described
Work as understanding, without departing from scope defined by the claims of the present invention, variations and modifications can be carried out to the present invention,
These technical solutions improved to the claims in the present invention each fall within protection scope of the present invention.
Claims (8)
1. a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation, which is characterized in that this method include with
Lower step:
1) in raw microwave traffic data, based on when window [t+ (n-1) T, t+nT) to irregular time point data carry out
It repairs, obtains standard time point data collection, T is the collection period of microwave detector；T is some standard time point, takes T integral multiple
Any time namely microwave detector at the time of carry out certain vehicle data typing；N is positive integer；
2) on the basis of standard time point data collection, according to the flow of every vehicle data, speed and time occupancy three categories
Property value condition is identified and is repaired to attribute abnormal data, and attribute abnormal repair data collection is obtained；
3) on the basis of attribute abnormal repair data collection, flow abnormal data is identified and is repaired, obtained abnormal microwave and hand over
Valid data collection after logical data reparation；
4) speed, flow and the time occupancy concentrated according to valid data, identifies traffic congestion region.
2. a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation according to claim 1, special
Sign is, when the raw microwave traffic data refers to that motor vehicle crosses microwave detector, detector is every a collection period
Just a vehicle data typing is carried out, every data included vehicle time, lane number, flow, speed and time occupancy.
3. a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation according to claim 1, special
Sign is, repairs as follows to irregular time point data in the step 1):
1.1) it initializes, enables n=1；
If window when 1.2) [t+ (n-1) T, t+nT) in without vehicle data, then the period is denoted as the shortage of data period and gone forward side by side
Row is rejected, and is entered step 1.5), is otherwise entered step 1.3)；
If window when 1.3) [t+ (n-1) T, t+nT) in an only vehicle data, then by the speed of the vehicle data, stream
When amount, time occupancy vehicle attribute value are as standard time point t+ (n-1) T, the speed of vehicle data, flow, time are accounted for
It with rate attribute value, enters step 1.5), otherwise enters step 1.4)；
1.4) this constantly window [t+ (n-1) T, t+nT) in have a plurality of vehicle data, then by all vehicle datas in window when this
Speed, flow, time occupancy attribute mean value as standard time point t+ (n-1) T when, speed, stream in vehicle data
Amount, time occupancy attribute value；
1.5) n=n+1 is enabled, if n≤N, return step 1.1) vehicle data in window of lower a period of time is judged, otherwise export
The revised data set of vehicle data namely standard time point data collection, whereinToIndicate the inspection of microwave detector
Survey total duration.
4. a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation according to claim 1, special
Sign is, identifies as follows to attribute abnormal data in the step 2):
2.1) it initializes, enables m=1；
2.2) it is concentrated in standard time point data, if when standard time point t+mT, the speed attribute value V of vehicle datat+m·T, stream
Measure attribute value Qt+m·T, time occupancy attribute value Dt+m·TIt " does not lack ", then enters step 2.3), otherwise by the standard time
The vehicle data of point is denoted as attribute missing data, enters step 2.5)；
2.3) when according to following below scheme to standard time point t+mT, speed, the flow attribution value of vehicle data are differentiated:
If Step a Vt+m·T<1.25·VDAnd Qt+m·T2.4) < C then enters step, otherwise enters step b；
If Step b Vt+m·T>1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as speed attribute and exceeded by < C
2.4) data enter step, otherwise enter step c；
If Step c Vt+m·T<1.25·VDAnd Qt+m·TThe vehicle data of the standard time point is then denoted as flow attribution and exceeded by > C
2.4) data, enter step, be otherwise denoted as speed and flow attribution beyond data, enter step 2.4)；
If 2.4) in the vehicle data of standard time point t+mT, Vt+m·T、Qt+m·T、Dt+m·TIn exist simultaneously numerical value equal to 0 and
The vehicle data of the standard time point is then denoted as attribute error data, entered step 2.5), otherwise table by the attribute not equal to 0
Speed, flow attribution value when bright standard time point t+mT is normal, is directly entered step 2.5)；
2.5) m=m+1 is enabled, if m≤M, M are the data volume of standard data set, then return step 2.2) to next standard time point
Vehicle data judged that otherwise output attribute missing data, attribute exceed data, attribute error data, and be referred to as belonging to
Sexual abnormality data.
5. a kind of congestion regions identification side based on abnormal microwave traffic data reparation according to claim 1,2,3 or 4
Method, which is characterized in that attribute abnormal data are repaired in the step 2), are the history numbers according to same microwave detector
According to progress according to the following formula:
Wherein,It respectively indicates in the abnormal attribute data that standard time point is t+iT, speed, stream
Value after amount, the reparation of time occupancy attribute, i is positive integer, Vt+(i-2)·T、Vt+(i-1)·T、Vt+(i+1)·T、Vt+(i+2)·TTable respectively
Show microwave detector typing when standard time point is t+ (i-2) T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T
The speed attribute value of vehicle data, Qt+(i-2)·T、Qt+(i-1)·T、Qt+(i+1)·T、Qt+(i+2)·TRespectively indicating standard time point is t+
(i-2) when T, t+ (i-1) T, t+ (i+1) T, t+ (i+2) T the vehicle data of the microwave detector typing flow category
Property value, Dt+(i-2)·T、Dt+(i-1)·T、Dt+(i+1)·T、Dt+(i+2)·TRespectively indicating standard time point is t+ (i-2) T, t+ (i-1)
T, when t+ (i+1) T, t+ (i+2) T the vehicle data of the microwave detector typing time occupancy attribute value.
6. a kind of congestion regions identification side based on abnormal microwave traffic data reparation according to claim 1,2,3 or 4
Method, which is characterized in that attribute abnormal data are repaired in the step 2), are the numbers according to the adjacent detector same period
According to progress according to the following formula:
Wherein,Respectively indicate standard time point be t+iT abnormal attribute data in, speed, flow,
Time occupancy attribute reparation value,Microwave when standard time point is t+iT is respectively indicated to examine
The speed attribute value of the vehicle data of four adjacent microwave detector typings of device front and back is surveyed,Point
Not Biao Shi the adjacent four microwave detector typings before and after microwave detector when being t+nT of standard time point vehicle data
Flow attribution value,It respectively indicates when standard time point is t+iT before and after the microwave detector
The time occupancy attribute value of the vehicle data of four adjacent microwave detector typings.
7. a kind of according to claim 1, congestion regions identification based on abnormal microwave traffic data reparation described in 2,3,4 or 5
Method, which is characterized in that flow abnormal data is identified as follows in the step 3):
3.1) it is concentrated in attribute abnormal repair data, takes the flow attribution value of four groups of vehicle datas at adjacent modular time point
Qt+(j-2)·T、Qt+(j-1)·T、Qt+j·T、Qt+(j+1)·TMedian construct primary smooth sequence
3.2) it takesMedian construct secondary smooth sequence
3.3) it enablesConstruct smooth sequence three times
3.4) it calculatesWith Qt+j·TRoot-mean-square errorM is the number of standard data set
According to amount and the data volume of attribute abnormal repair data collection；
3.5) when taking standard time point t+jT, the flow attribution value of vehicle data is maximum, minimum value is respectively as follows:
If 3.6)Data on flows when then thinking standard time point t+jT is different
The flow attribution value of vehicle data is abnormal often namely when standard time point t+jT, needs to be modified, otherwise it is assumed that the flow
Normally, without being modified.
8. a kind of congestion regions recognition methods based on abnormal microwave traffic data reparation according to claim 7, special
Sign is, in the step 3), according to multiple linear regression, repairs according to the following formula to flow abnormal data:
Ct+u·T=a0+a1·1Qt+u·T+a2·2Qt+u·T+…ar·rQt+u·T+e
Wherein, Ct+n·TFor the value after the abnormal flow data correction of standard time point t+nT,1Qt+u·T、2Qt+u·T、…、rQt+u·T
Device r normal discharge data, a in the collected history of same standard time point t+uT are surveyed for the microwave0For constant term, a1、
a2…arFor regression coefficient, e is random error.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018114667004 | 2018-12-03 | ||
| CN201811466700 | 2018-12-03 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109830101A true CN109830101A (en) | 2019-05-31 |
Family
ID=66863475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910109047.4A Pending CN109830101A (en) | 2018-12-03 | 2019-02-03 | A kind of congestion regions recognition methods based on abnormal microwave traffic data reparation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109830101A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783681A (en) * | 2021-01-22 | 2021-05-11 | 广东电网有限责任公司东莞供电局 | Self-service big data multistage closed loop restoration method and device for power enterprise |
| CN114764977A (en) * | 2022-04-06 | 2022-07-19 | 成都亿盟恒信科技有限公司 | Road congestion calculation method and system based on driving data |
| CN116311930A (en) * | 2023-03-15 | 2023-06-23 | 河北省交通规划设计研究院有限公司 | Traffic flow state data time gathering method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004355537A (en) * | 2003-05-30 | 2004-12-16 | Matsushita Electric Ind Co Ltd | Traffic flow data prediction device and method |
| CN102968901A (en) * | 2012-11-30 | 2013-03-13 | 青岛海信网络科技股份有限公司 | Method for acquiring regional congestion information and regional congestion analyzing device |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN108830162A (en) * | 2018-05-21 | 2018-11-16 | 西华大学 | Time series pattern sequential extraction procedures method and storage method in monitoring radio-frequency spectrum data |
-
2019
- 2019-02-03 CN CN201910109047.4A patent/CN109830101A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004355537A (en) * | 2003-05-30 | 2004-12-16 | Matsushita Electric Ind Co Ltd | Traffic flow data prediction device and method |
| CN102968901A (en) * | 2012-11-30 | 2013-03-13 | 青岛海信网络科技股份有限公司 | Method for acquiring regional congestion information and regional congestion analyzing device |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN108830162A (en) * | 2018-05-21 | 2018-11-16 | 西华大学 | Time series pattern sequential extraction procedures method and storage method in monitoring radio-frequency spectrum data |
Non-Patent Citations (1)
| Title |
|---|
| 邹晓芳: "《城市快速路交通流故障数据修复方法研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783681A (en) * | 2021-01-22 | 2021-05-11 | 广东电网有限责任公司东莞供电局 | Self-service big data multistage closed loop restoration method and device for power enterprise |
| CN112783681B (en) * | 2021-01-22 | 2022-11-22 | 广东电网有限责任公司东莞供电局 | Self-service big data multistage closed loop restoration method and device for power enterprise |
| CN114764977A (en) * | 2022-04-06 | 2022-07-19 | 成都亿盟恒信科技有限公司 | Road congestion calculation method and system based on driving data |
| CN116311930A (en) * | 2023-03-15 | 2023-06-23 | 河北省交通规划设计研究院有限公司 | Traffic flow state data time gathering method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104408925B (en) | Crossing evaluation of running status method based on display radar | |
| CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
| CN103839409B (en) | Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis | |
| CN101710448B (en) | Road traffic state detecting device based on omnibearing computer vision | |
| CN109830101A (en) | A kind of congestion regions recognition methods based on abnormal microwave traffic data reparation | |
| CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
| CN107085943B (en) | Short-term prediction method and system for road travel time | |
| CN109376935B (en) | Bus passenger flow time interval combined prediction method based on neural network | |
| CN110807919A (en) | Urban road network traffic operation situation evaluation method based on vehicle passing data | |
| CN103985250A (en) | Light-weight holographic road traffic state visual inspection device | |
| CN104484994A (en) | Urban road network traffic operation index evaluation method and device based on array radar | |
| CN104700630A (en) | Method and system for monitoring vehicle flow of highway | |
| CN105513362B (en) | A kind of bus platform adjacent area bus running state evaluation verification method | |
| CN113935158B (en) | Traffic detector optimal layout method for multiple points of expressway accident | |
| CN115691120A (en) | Congestion identification method and system based on highway running water data | |
| CN114841712B (en) | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment | |
| CN115995149A (en) | Multi-source data-based parking supply and demand characteristic dynamic evaluation method and system | |
| CN113393113B (en) | Method and system for tracing parking fee evasion in road based on theoretical credit evaluation of complex network | |
| CN104575049A (en) | Viaduct ramp intelligent inducing control method and device based on array radars | |
| CN117173899B (en) | Smart city traffic travel quality evaluation method | |
| CN112907088B (en) | Parameter adjustment method and system for score-clearing model | |
| CN105070075A (en) | Trunk line self-optimization signal control method based on array radar and device | |
| CN105303833B (en) | Overpass accident method of discrimination based on microwave vehicle detector | |
| CN103700264A (en) | Computation method of expressway section travel speed based on ETC (Electronic Toll Collection) data | |
| CN114078321A (en) | Traffic condition determination method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |